© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107330
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ³éĶ®æŶåĪ»
    -0.29
     Rit
    -0.27
    lesi
    -0.26
    æŀ¥
    -0.25
    çŃ·
    -0.24
    çŃ·åŃIJ
    -0.24
     static
    -0.24
     insurance
    -0.24
    banner
    -0.24
    èıľ
    -0.24
    POSITIVE LOGITS
    ifferential
    0.29
    丰ç¡ķ
    0.25
    å¼Ł
    0.25
    AAF
    0.25
    oes
    0.25
    å½ĵæĪIJ
    0.24
    å¿ĥè¡Ģ
    0.24
    Tho
    0.24
     diá
    0.24
    大èĦij
    0.24
    Activations Density 9.557%

    No Known Activations